INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.10

6:0.08

7:0.08

8:0.10

9:0.06

10:0.07

11:0.07

Negative Logits

 CrossRef

-1.97

 Facebook

-1.65

CVE

-1.64

jamin

-1.61

));

-1.55

 YouTube

-1.55

 Purple

-1.54

 Stanford

-1.54

 Huawei

-1.54

 GitHub

-1.53

POSITIVE LOGITS

agara

1.86

 contrace

1.85

cale

1.76

omorph

1.73

only

1.65

omer

1.62

axis

1.61

 bonding

1.61

oooooooo

1.60

AAAA

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.